arXiv subjects

Shuo Zhang

Publications and source records attributed to Shuo Zhang.

At least 163 records · Page 9Linked to original sources

arXiv2024

Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection

Knowledge distillation based on student-teacher network is one of the mainstream solution paradigms for the challenging unsupervised Anomaly Detection task, utilizing the difference in representation capabilities of the teacher and student networks to implement anomaly localization. However, over-generalization of the student network to the teacher network may lead to negligible differences in representation capabilities of anomaly, thus affecting the detection effectiveness. Existing methods address the possible over-generalization by using differentiated students and teachers from the structural perspective or explicitly expanding distilled information from the content perspective, which inevitably result in an increased likelihood of underfitting of the student network and poor anomaly detection capabilities in anomaly center or edge. In this paper, we propose Dual-Modeling Decouple Distillation (DMDD) for the unsupervised anomaly detection. In DMDD, a Decouple Student-Teacher Network is proposed to decouple the initial student features into normality and abnormality features. We further introduce Dual-Modeling Distillation based on normal-anomaly image pairs, fitting normality features of anomalous image and the teacher features of the corresponding normal image, widening the distance between abnormality features and the teacher features in anomalous regions. Synthesizing these two distillation ideas, we achieve anomaly detection which focuses on both edge and center of anomaly. Finally, a Multi-perception Segmentation Network is proposed to achieve focused anomaly map fusion based on multiple attention. Experimental results on MVTec AD show that DMDD surpasses SOTA localization performance of previous knowledge distillation-based methods, reaching 98.85% on pixel-level AUC and 96.13% on PRO.

cs.CV↗

arXiv2024

Circuit-Noise-Resilient Virtual Distillation

Quantum error mitigation (QEM) is vital for improving quantum algorithms' accuracy on noisy near-term devices. A typical QEM method, called Virtual Distillation (VD), can suffer from imperfect implementation, potentially leading to worse outcomes than without mitigation. To address this, we introduce Circuit-Noise-Resilient Virtual Distillation (CNR-VD), which includes a calibration process using simple input states to enhance VD's performance despite circuit noise, aiming to recover the results of an ideally conducted VD circuit. Simulations show that CNR-VD significantly mitigates noise-induced errors in VD circuits, boosting accuracy by up to tenfold over standard VD. It provides positive error mitigation even under high noise, where standard VD fails. Furthermore, our estimator's versatility extends its utility beyond VD, enhancing outcomes in general Hadamard-Test circuits. The proposed CNR-VD significantly enhances the noise-resilience of VD, and thus is anticipated to elevate the performance of quantum algorithm implementations on near-term quantum devices.

quant-ph↗

arXiv2024

Quantum Advantage: A Single Qubit's Experimental Edge in Classical Data Storage

We implement an experiment on a photonic quantum processor establishing efficacy of the elementary quantum system in classical information storage. The advantage is established by considering a class of simple bipartite games played with the communication resource qubit and classical bit (c-bit), respectively. Conventional wisdom, supported by the no-go theorems of Holevo and Frenkel-Weiner, suggests that such a quantum advantage is unattainable when the sender and receiver share randomness or classical correlations. However, our results reveal a quantum advantage in a scenario devoid of any shared randomness. Our experiment involves the development of a variational triangular polarimeter, enabling the realization of positive operator value measurements crucial for establishing the targeted quantum advantage. Beyond showcasing a robust communication advantage with a single qubit, our work paves the way for immediate applications in near-term quantum technologies. It provides a semi-device-independent certification scheme for quantum encoding-decoding systems and offers an efficient method for information loading and transmission in quantum networks.

quant-ph↗

arXiv2024

Enhancing Question Answering on Charts Through Effective Pre-training Tasks

To completely understand a document, the use of textual information is not enough. Understanding visual cues, such as layouts and charts, is also required. While the current state-of-the-art approaches for document understanding (both OCR-based and OCR-free) work well, a thorough analysis of their capabilities and limitations has not yet been performed. Therefore, in this work, we addresses the limitation of current VisualQA models when applied to charts and plots. To investigate shortcomings of the state-of-the-art models, we conduct a comprehensive behavioral analysis, using ChartQA as a case study. Our findings indicate that existing models particularly underperform in answering questions related to the chart's structural and visual context, as well as numerical information. To address these issues, we propose three simple pre-training tasks that enforce the existing model in terms of both structural-visual knowledge, as well as its understanding of numerical questions. We evaluate our pre-trained model (called MatCha-v2) on three chart datasets - both extractive and abstractive question datasets - and observe that it achieves an average improvement of 1.7% over the baseline model.

cs.CL↗

arXiv2024

Discovery of interstellar 1-cyanopyrene: a four-ring polycyclic aromatic hydrocarbon in TMC-1

Polycyclic aromatic hydrocarbons (PAHs) are expected to be the most abundant class of organic molecules in space. Their interstellar lifecycle is not well understood, and progress is hampered by difficulties detecting individual PAH molecules. Here, we present the discovery of CN-functionalized pyrene, a 4-ring PAH, in the dense cloud TMC-1 using the 100-m Green Bank Telescope. We derive an abundance of 1-cyanopyrene of ~1.52 x $10^{12}$ cm$^{-2}$, and from this estimate that the un-substituted pyrene accounts for up to ~0.03-0.3% of the carbon budget in the dense interstellar medium which trace the birth sites of stars and planets. The presence of pyrene in this cold (~10 K) molecular cloud agrees with its recent measurement in asteroid Ryugu where isotopic clumping suggest a cold, interstellar origin. The direct link to the birth site of our solar system is strengthened when we consider the solid state pyrene content in the pre-stellar materials compared to comets, which represent the most pristine material in the solar system. We estimate that solid state pyrene can account for 1% of the carbon within comets carried by this one single organic molecule. The abundance indicates pyrene is an "island of stability" in interstellar PAH chemistry and suggests a potential cold molecular cloud origin of the carbon carried by PAHs that is supplied to forming planetary systems, including habitable worlds such as our own.

astro-ph.GA↗

arXiv2024

Detections of interstellar 2-cyanopyrene and 4-cyanopyrene in TMC-1

Polycyclic aromatic hydrocarbons (PAHs) are among the most ubiquitous compounds in the universe, accounting for up to ~25% of all interstellar carbon. Since most unsubstituted PAHs do not possess permanent dipole moments, they are invisible to radio astronomy. Constraining their abundances relies on the detection of polar chemical proxies, such as aromatic nitriles. We report the detection of 2- and 4-cyanopyrene, isomers of the recently detected 1-cyanopyrene. We find that these isomers are present in an abundance ratio of ~2:1:2, which mirrors the number of equivalent sites available for CN addition. We conclude that there is evidence that the cyanopyrene isomers formed by direct CN addition to pyrene under kinetic control in hydrogen-rich gas at 10 K and discuss constraints on the H/CN ratio for PAHs in TMC-1.

astro-ph.GA↗

arXiv2024

Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation

Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network. This strategy tends to generate safe responses due to the mutual restriction between emotion and semantics, and requires rare emotion-annotated large-scale dialogue corpus. Inspired by the "think twice" behavior in human dialogue, we propose a two-stage conversational agent for the generation of emotional dialogue. Firstly, a dialogue model trained without the emotion-annotated dialogue corpus generates a prototype response that meets the contextual semantics. Secondly, the first-stage prototype is modified by a controllable emotion refiner with the empathy hypothesis. Experimental results on the DailyDialog and EmpatheticDialogues datasets demonstrate that the proposed conversational outperforms the comparison models in emotion generation and maintains the semantic performance in automatic and human evaluations.

cs.CL↗

arXiv2024

Seed-Music: A Unified Framework for High Quality and Controlled Music Generation

We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music generation with performance controls from multi-modal inputs, including style descriptions, audio references, musical scores, and voice prompts. For post-production editing, it offers interactive tools for editing lyrics and vocal melodies directly in the generated audio. We encourage readers to listen to demo audio examples at https://team.doubao.com/seed-music "https://team.doubao.com/seed-music".

cs.SD↗

arXiv2024

Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models

Large Multimodal Models (LMMs) have shown promise in vision-language tasks but struggle with high-resolution input and detailed scene understanding. Addressing these challenges, we introduce Monkey to enhance LMM capabilities. Firstly, Monkey processes input images by dividing them into uniform patches, each matching the size (e.g., 448x448) used in the original training of the well-trained vision encoder. Equipped with individual adapter for each patch, Monkey can handle higher resolutions up to 1344x896 pixels, enabling the detailed capture of complex visual information. Secondly, it employs a multi-level description generation method, enriching the context for scene-object associations. This two-part strategy ensures more effective learning from generated data: the higher resolution allows for a more detailed capture of visuals, which in turn enhances the effectiveness of comprehensive descriptions. Extensive ablative results validate the effectiveness of our designs. Additionally, experiments on 18 datasets further demonstrate that Monkey surpasses existing LMMs in many tasks like Image Captioning and various Visual Question Answering formats. Specially, in qualitative tests focused on dense text question answering, Monkey has exhibited encouraging results compared with GPT4V. Code is available at https://github.com/Yuliang-Liu/Monkey.

cs.CV↗

arXiv2024

Spin-2 operators in two-dimensional $\mathcal{N}=(4,0)$ quivers from massive type IIA

In this work we revisit the problem of studying spin-2 fluctuations around a class of solutions in massive type IIA that is given by a warped $\text{AdS}_3 \times \text{S}^2 \times \text{T}^4 \times \mathcal{I}_ρ$ and with $\mathcal{N}=(4,0)$ supersymmetry. We were able to identify a class of fluctuations, which is known as the ``minimal universal class'' that is independent of the background data and saturates the bound on the mass related to the field theory unitarity bound. These operators have conformal dimension $Δ= 2(\ell+1)$, with $\ell$ being the quantum number of the angular momentum on the $\text{S}^2$. We also computed the normalisation of the $2$-point function of stress-energy tensors from the effective $3$-dimensional graviton action. We comment on the relation of our results to the related $\text{AdS}_3$ and $\text{AdS}_2$ solutions in massive type IIA and type IIB theories respectively.

hep-th↗

arXiv2024

LLaSA: Large Language and E-Commerce Shopping Assistant

The e-commerce platform has evolved rapidly due to its widespread popularity and convenience. Developing an e-commerce shopping assistant for customers is crucial to aiding them in quickly finding desired products and recommending precisely what they need. However, most previous shopping assistants face two main problems: (1) task-specificity, which necessitates the development of different models for various tasks, thereby increasing development costs and limiting effectiveness; and (2) poor generalization, where the trained model performs inadequately on up-to-date products. To resolve these issues, we employ Large Language Models (LLMs) to construct an omnipotent assistant, leveraging their adeptness at handling multiple tasks and their superior generalization capability. Nonetheless, LLMs lack inherent knowledge of e-commerce concepts. To address this, we create an instruction dataset comprising 65,000 samples and diverse tasks, termed as EshopInstruct. Through instruction tuning on our dataset, the assistant, named LLaSA, demonstrates the potential to function as an omnipotent assistant. Additionally, we propose various inference optimization strategies to enhance performance with limited inference resources. In the Amazon KDD Cup 2024 Challenge, our proposed method, LLaSA, achieved an overall ranking of 3rd place on ShopBench, including 57 tasks and approximately 20,000 questions, and we secured top-5 rankings in each track, especially in track4, where we achieved the best performance result among all student teams. Our extensive practices fully demonstrate that LLMs possess the great potential to be competent e-commerce shopping assistants.

cs.CL↗

arXiv2024

Efficient Training of Large Language Models on Distributed Infrastructures: A Survey

Large Language Models (LLMs) like GPT and LLaMA are revolutionizing the AI industry with their sophisticated capabilities. Training these models requires vast GPU clusters and significant computing time, posing major challenges in terms of scalability, efficiency, and reliability. This survey explores recent advancements in training systems for LLMs, including innovations in training infrastructure with AI accelerators, networking, storage, and scheduling. Additionally, the survey covers parallelism strategies, as well as optimizations for computation, communication, and memory in distributed LLM training. It also includes approaches of maintaining system reliability over extended training periods. By examining current innovations and future directions, this survey aims to provide valuable insights towards improving LLM training systems and tackling ongoing challenges. Furthermore, traditional digital circuit-based computing systems face significant constraints in meeting the computational demands of LLMs, highlighting the need for innovative solutions such as optical computing and optical networks.

cs.DC↗

arXiv2024

JuliVQC: an Efficient Variational Quantum Circuit Simulator for Near-Term Quantum Algorithms

We introduce JuliVQC: a light-weight, yet extremely efficient variational quantum circuit simulator. JuliVQC is part of an effort for classical simulation of the \textit{Zuchongzhi} quantum processors, where it is extensively used to characterize the circuit noises, as a building block in the Schr$\ddot{\text{o}}$dinger-Feynman algorithm for classical verification and performance benchmarking, and for variational optimization of the Fsim gate parameters. The design principle of JuliVQC is three-fold: (1) Transparent implementation of its core algorithms, realized by using the high-performance script language Julia; (2) Efficiency is the focus, with a cache-friendly implementation of each elementary operations and support for shared-memory parallelization; (3) Native support of automatic differentiation for both the noiseless and noisy quantum circuits. We perform extensive numerical experiments on JuliVQC in different application scenarios, including quantum circuits, variational quantum circuits and their noisy counterparts, which show that its performance is among the top of the popular alternatives.

quant-ph↗

arXiv2024

Improving Large Models with Small models: Lower Costs and Better Performance

Pretrained large models (PLMs), such as ChatGPT, have demonstrated remarkable performance across diverse tasks. However, the significant computational requirements of PLMs have discouraged most product teams from running or fine-tuning them. In such cases, to harness the exceptional performance of PLMs, one must rely on expensive APIs, thereby exacerbating the economic burden. Despite the overall inferior performance of small models, in specific distributions, they can achieve comparable or even superior results. Consequently, some input can be processed exclusively by small models. On the other hand, certain tasks can be broken down into multiple subtasks, some of which can be completed without powerful capabilities. Under these circumstances, small models can handle the simple subtasks, allowing large models to focus on challenging subtasks, thus improving the performance. We propose Data Shunt$^+$ (DS$^+$), a general paradigm for collaboration of small and large models. DS$^+$ not only substantially reduces the cost associated with querying large models but also effectively improves large models' performance. For instance, ChatGPT achieves an accuracy of $94.43\%$ on Amazon Product sentiment analysis, and DS$^+$ achieves an accuracy of $95.64\%$, while the cost has been reduced to only $31.18\%$. Besides, experiments also prove that the proposed collaborative-based paradigm can better inject specific task knowledge into PLMs compared to fine-tuning.

cs.CL↗

arXiv2024

Diffuse X-ray Explorer: a high-resolution X-ray spectroscopic sky surveyor on the China Space Station

DIffuse X-ray Explorer (DIXE) is a proposed high-resolution X-ray spectroscopic sky surveyor on the China Space Station (CSS). DIXE will focus on studying hot baryons in the Milky Way. Galactic hot baryons like the X-ray emitting Milky Way halo and eROSITA bubbles are best observed in the sky survey mode with a large field of view. DIXE will take advantage of the orbital motion of the CSS to scan a large fraction of the sky. High-resolution X-ray spectroscopy, enabled by superconducting microcalorimeters based on the transition-edge sensor (TES) technology, will probe the physical properties (e.g., temperature, density, elemental abundances, kinematics) of the Galactic hot baryons. This will complement the high-resolution imaging data obtained with the eROSITA mission. Here we present the preliminary design of DIXE. The payload consists mainly of a detector assembly and a cryogenic cooling system. The key components of the detector assembly are a microcalorimeter array and frequency-domain multiplexing readout electronics. To provide a working temperature for the detector assembly, the cooling system consists of an adiabatic demagnetization refrigerator and a mechanical cryocooler system.

astro-ph.IM↗

arXiv2024

The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models

Large language models often necessitate grounding on external knowledge to generate faithful and reliable answers. Yet even with the correct groundings in the reference, they can ignore them and rely on wrong groundings or their inherent biases to hallucinate when users, being largely unaware of the specifics of the stored information, pose questions that might not directly correlate with the retrieved groundings. In this work, we formulate this knowledge alignment problem and introduce MixAlign, a framework that interacts with both the human user and the knowledge base to obtain and integrate clarifications on how the user question relates to the stored information. MixAlign employs a language model to achieve automatic knowledge alignment and, if necessary, further enhances this alignment through human user clarifications. Experimental results highlight the crucial role of knowledge alignment in boosting model performance and mitigating hallucination, with improvements noted up to 22.2% and 27.1% respectively. We also demonstrate the effectiveness of MixAlign in improving knowledge alignment by producing high-quality, user-centered clarifications.

cs.CL↗

arXiv2024

More on spin-2 operators in holographic quantum mechanics

We study the spectrum, unitarity bound and holographic central charge of spin-2 operators in a warped $\text{AdS}_2 \times \text{S}^2 \times \text{T}^4 \times \mathcal{I}_ψ\times \mathcal{I}_ρ$ background in the Type IIB theory. We were able to identify a class of solutions that is completely independent of the functions that define the background solution. We comment on the relation of our results to the previous ones in the literature.

hep-th↗

arXiv2024

Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as a foundation model for speech generation and excels in speech in-context learning, achieving performance in speaker similarity and naturalness that matches ground truth human speech in both objective and subjective evaluations. With fine-tuning, we achieve even higher subjective scores across these metrics. Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild. Furthermore, we propose a self-distillation method for speech factorization, as well as a reinforcement learning approach to enhance model robustness, speaker similarity, and controllability. We additionally present a non-autoregressive (NAR) variant of the Seed-TTS model, named $\text{Seed-TTS}_\text{DiT}$, which utilizes a fully diffusion-based architecture. Unlike previous NAR-based TTS systems, $\text{Seed-TTS}_\text{DiT}$ does not depend on pre-estimated phoneme durations and performs speech generation through end-to-end processing. We demonstrate that this variant achieves comparable performance to the language model-based variant and showcase its effectiveness in speech editing. We encourage readers to listen to demos at \url{https://bytedancespeech.github.io/seedtts_tech_report}.

eess.AS↗